Changes

Summary

1. New stoc vol file (details)
2. Done with implementation stochastic volatility with no hyper-parameters (details)
3. Stochastic volatility (details)
4. answers to Alessio comments (details)
5. started with solver (details)
6. stoc vol works. TODO: implement diagnostics (details)
7. started with total order implementation (details)
8. working on MixedOrder class. (details)
9. working on mixed order (details)
10. working on MixedOrder (details)
11. Added diagnostic routines (details)
12. merged into toolbox (details)
13. working on stocVol example (details)
14. stocVol (details)
15. stocVol (details)
16. added matplotlib dependency (details)
17. working on banana example (details)
18. documenting banana (details)
19. working on banana (details)
20. working on banana example (details)
21. banana example needs documentation regarding diagnostics (details)
22. added some diagnostics (details)
23. working on laplace_approximation function (details)
24. laplace (details)
25. working on optimizer (details)
26. Laplace approx done. To be tested. (details)
27. working on FrozenGaussian with precision input (details)
28. tests passed for new version of GaussianDensity. TODO: add unittests (details)
29. done precision tests (details)
30. laplace works. to finish tests (details)
31. laplace works. to finish tests (details)
32. laplace works. to finish tests (details)
33. Laplace ready (details)
34. test optimizer (details)
35. working on optimizer (details)
36. fixed optimizer (details)
37. optimizer works! (details)
38. added some docs on banana (details)
39. added some logging in the Diagnostic module. To be added all over. (details)
40. newton_cglu_optimizer (details)
41. added function niceplot (details)
42. Added class TransportMap (details)
43. class TransportMap integrated (details)
44. Init maps (details)
45. working on the CommonBase LinearSpan TM (details)
46. Removed duplicate pullback functions (details)
47. working on CommonBase LinearSpan Map (details)
48. linear transport map (details)
49. fixed naming of TransportMaps (details)
50. working on CommonBase LinearSpan Map (details)
51. working on CommonBase LinearSpan Map (details)
52. Done CommonBasis LinearSpan Map. Moving to (details)
53. working on CommonBasisLinearSpanApproximation (details)
54. working on CommonBasisLinearSpanApproximation (details)
55. working on CommBase Map (details)
56. moving function evaluation and gradients into LineaSpanAppoximation (details)
57. Done with linear map class. Now moving to unit test (details)
58. in process of migrating functions from FullLinearSpan to LinearSpan with (details)
59. moved most of the stuff to LinearSpan (details)
60. moved most of the stuff to LinearSpan (details)
61. LinearSpanApproximations ready. Move to TriangularTransportMap (details)
62. Minor changes (details)
63. changed uml (details)
64. Added plotAlignedSliceMap (details)
65. Added niceContour, plot2density and testBananaPullback (details)
66. added testBananaPullback (details)
67. fixed l2 regularization (details)
68. rotated banana improved (details)
69. working on #36. Done with Transport maps? (details)
70. Banana example linear span (details)
71. some mods on the examples (details)
72. #26 working on TM densities test cases (details)
73. working on test cases (details)
74. working on test cases (details)
75. working on density test cases (details)
76. working on test cases for densities (details)
77. working on dens test cases (details)
78. working on tests densities (details)
79. transport map densities tests added. Still some problems on the linear (details)
80. added tests for kl_divergence (details)
81. removed old tests structure (details)
82. #26 fixed all unittests. TODO add test for LinearTransportMap (Alessio) (details)
83. updating UML graph and TransportMap classes (details)
84. Fixes #27: UML graph updated (details)
85. fixed import name for CommonBasisLinearSpanTriangularTransportMap (details)
86. relaxed target eps in MC tests for density unittests (details)
87. Jenkins test develop script added (details)
88. fixed test_develop chmod (details)
89. #25 restructuring precomp strategy in order to enrich the precomp (details)
90. #25 restructuring precomp strategy in order to enrich the precomp (details)
91. #25 restructuring precomp strategy in order to enrich the precomp (details)
92. uni-variate preallocation works for linear system (details)
93. working on TransportMapBase to allow both uni-variate and multi-variate (details)
94. working on TransportMapBase to allow both uni-variate and multi-variate (details)
95. #25 linear span transport maps with precomputation of uni-variate and (details)
96. working on IntegratedExp approximation (details)
97. working on IntegratedExp approximation (details)
98. working on IntegratedExp approximation (details)
99. working on precomputation in integrated exponential. Some tests fail... (details)
100. #25 preomputation on integrated exponential works! Make comprehensive (details)
101. fixed FrozenFunction precomp functions (details)
102. KLdivergence example with options (details)
103. working on common basis (details)
104. working on common basis (details)
105. fixing common basis (details)
106. CommonBasisLinearSpan ready. TODO: unittests (details)
107. making unittests for CommonBasisLinearSpan (details)
108. fixed stoc Vol with constant term (details)
109. CommonBasis LinearSpan works. Moving to IntegratedExponential (details)
110. CommonBasisIntExp started. precomp_evaluate done (details)
111. IntExpFunctionApproximation precomputation structure refactorization (details)
112. refactored IntExpFuncApproximation (details)
113. working on CommonBasis IntegExp (details)
114. CommonBasis IntegratedExponential works (details)
115. KLdivergence example now uses CommonBasis implementation (details)
116. Fixes #25. (details)
117. updated banana example with common basis (details)
118. TotalOrder approximation added. Fix the integration into IntExp (details)
119. Total order working on test_transportmaps. TODO: Add (details)
120. Total Order unittests done (details)
121. fixed CommonBasis precomputation, adding to_compute_flag (details)
122. Fixes #1. Total order truncation implemented. Updated KLdivergence (details)
123. Added BOD model and ConditionedDiffusion folders (details)
124. fixed conflict on testBananaPullback (details)
125. started with new branch (details)
126. fixed bug on GaussianDensity rvs (details)
127. fixed bug on GaussianDensity rvs (details)
128. working on stochastic volatility example (details)
129. Added joint BOD model (details)
130. reshaping StochasticVolatility example (details)
131. BOD model works. (details)
132. Stochastic volatility issuing command changed (details)
133. #31 started optional vectorization of expectations in (details)
134. Notes composition map Stoc Vol (details)
135. Added banana folder (details)
136. starting with stoc vol composition (details)
137. split map generation from StochasticVolatility files (details)
138. Added gradients composition (details)
139. Added gradients composition (details)
140. Added Markov Component Stoc Vol (details)
141. stoc vol composition almost there.... (details)
142. stoc vol composition runs. TODO: compose all the maps (details)
143. working on lifting and overall pullback (details)
144. stochastic volatility composition works!!! (details)
145. refactoring the vectorization in several routines... to be finished. (details)
146. #31 refactoring to allow computations in batches (details)
147. refactored everything to execute in batches defined by a list (iterable) (details)
148. new implementation works on old unit tests (details)
149. current implementation works on unittests and KLdivergence example test (details)
150. setting up BOD model for higher dimension... (details)
151. Opens #20. Added logging capabilities in the minimize_kl_divergence (details)
152. working on BOD higher order (details)
153. working on bod (details)
154. working on KL divergence arctan function (details)
155. cleaned KL divergence file (details)
156. re-organized predefined densities (details)
157. added corresponding changes also in the LinearTransportMap class (details)
158. working on the tilted banana (details)
159. updating LinearTransportMap (details)
160. updating LinearTransportMap (details)
161. working on banana (details)
162. added default classes for Isotropic transport maps (details)
163. added default classes for Isotropic transport maps (details)
164. using default functions all over (details)
165. working on rotated banana (details)
166. #35 working on cached evaluations low-level (details)
167. #35 low-level caching for function evaluation implemented. TODO: check (details)
168. removed some all-equal statements (details)
169. changed handling of indices (details)
170. caching low level partial_xd done (details)
171. changed array_equal withing function evaluation with a same_coeffs_flag (details)
172. fixed FrozenTriangularTransportMaps (details)
173. Gradients conditional diffusion (details)
174. working on conditioned diffusion script. fixed inputs to StocVol (details)
175. conditioned diffusion running script ready (details)
176. using default TransportMap generation all over the place (details)
177. Implemented gradients Markov Component Cond Diff (details)
178. working on fixing stochastic volatility components. TODO: Fix the (details)
179. fixed full transport map with extra same_coeffs_flag (details)
180. Debugging Hessian CondDiff (details)
181. Fixed gradient Markov Component Conditioned Diffusion (details)
182. Added composition maps for conditione diffusion (details)
183. working on conditioned diffusion (details)
184. FullTransportMap does not need to redefine pullback and pushforward (details)
185. cond diffusion works. better parametrization is needed (RBF?) (details)
186. can recover precision matrix in 3d (details)
187. updating UML diagram (details)
188. map from samples now has a couple more distributions to sample from (details)
189. mapFromSamples also plots histograms of pullback against original (details)
190. removed "TranportMaps." tag from index (details)
191. compare map to analytical (details)
192. histogram plots a bit nicer (details)
193. working on using RBF in banana example (details)
194. preparing for high-level caching. Restructured precomp structure (details)
195. high-level caching is done. TODO: check it is doing what is required to (details)
196. the high-level caching and the computation in batches/parallel need to (details)
197. mfs looking good, need support map still (details)
198. updated interface min_kl_div in TransportMapBase (details)
199. removed low-level caching. added high-level caching. TODO: check that (details)
200. added test case for high-level caching. change idxs_list to idxs_slice (details)
201. test cases work. try it out on examples and then test performaces on BOD (details)
202. works on examples kldivergence. Check that caching is actually used (details)
203. #35 high-level caching successful. TODO: profile on the BOD example. (details)
204. turned pushforward to exp(log_pushforward) (details)
205. experimenting on the banana example (details)
206. fixed bug in TransportMapBase (details)
207. removed flag vectorize. batch_size determines whether vectorize or not (details)
208. updated examples without vectorize flags (details)
209. fixed kl_divergence routines with batches. list -> slice (details)
210. working on low-level caching (details)
211. working on low-level caching (details)
212. low-level caching works on test cases (details)
213. trying to improve the hess computation (details)
214. alternative solution (details)
215. added grad_a_squared with precomputed VVT (details)
216. removed same_coeffs_flag and added caching for partial_xd (details)
217. working on the banana (details)
218. reverted to grad_a instead of grad_a_squared (details)
219. polishing hess_a in IntegExp (details)
220. polishing hess_a (details)
221. polishing hessian little by little (details)
222. mfsSandia includes transform (details)
223. some improvements in hess_a_log_pullback (details)
224. working on banana (details)
225. fixed import to numpy.linalg (details)
226. fixed hessian with regularization (details)
227. adding missing files to conditioned diffusion (details)
228. working on stoch diff (details)
229. working on conditioned diffusion (details)
230. improving visualization in conditioned diffusion (details)
231. plot in place conditioned diffusion (details)
232. working on value at risk problem (details)
233. working on the banana (details)
234. working on banana (details)
235. adding missing files to conditioned diffusion (details)
236. working on stoch diff (details)
237. working on conditioned diffusion (details)
238. improving visualization in conditioned diffusion (details)
239. plot in place conditioned diffusion (details)
240. working on value at risk problem (details)
241. remove rare events (details)
242. starting the sparsity algorithm (details)
243. sandia samples: now asks whether right or left-tailed (details)
244. plot samples includes 1d analytic form (details)
245. sandia1d computes analytical pdf and kl between that and computed (details)
246. kl div in 1d needs approximation help (details)
247. pullback density in progress (details)
248. fixed pullback (details)
249. trying MSE ? instead of KL (details)
250. mse computation in development (details)
251. Open #8 (details)
252. added derivative checks tests for pushforward transport map densities. (details)
253. building up example for inverse construction (details)
254. set up kl using TM density (details)
255. examples work derivative free (details)
256. creating inverse gradients (details)
257. working on gradient (details)
258. checking gradient (details)
259. back to kl (details)
260. gradient inverse map works (details)
261. implemented gradient. to be checked with tests and stochastic volatility (details)
262. grad_a_log_pushforward passes the unit test. Check signs and fix (details)
263. grad_a_log_pushforward passes the unit test. Check signs and fix (details)
264. unit tests passed. Remove precomputation in minimization in order to (details)
265. inverse solution works. todo: profile to see whether some computations (details)
266. partition densities off (details)
267. working on banana example (details)
268. added no-plot option (details)
269. Open #19: written test functions for map from samples. The problem has (details)
270. maps from samples tests work fine (details)
271. working on composite and inverse transport maps, in order to do (details)
272. working on the missing composition functions (details)
273. adding missing functions (details)
274. added grad_x and hess_x functions to Composite maps. (details)
275. working on the banana example. transform the target to the pushforward (details)
276. adding necessary inverse functions for pushforward (details)
277. fixing banana with composition of maps (details)
278. updated UML diagram (details)
279. banana example works with composite densities (details)
280. mfs tests has laplace, needs reorg (details)
281. test cases using randomly generated coefficients work (details)
282. started with direct construction of the inverse sv transport. Added (details)
283. added default also for linear span approximations (details)
284. working on sv inverse transport (details)
285. woring on stoc vol (details)
286. working on cond diffustion (details)
287. small changes in defaluts (details)
288. Default option poly and rbf (details)
289. added rbf/poly option to cond diffusion (details)
290. working on storage and reload of computed maps (details)
291. construction and postprocessing scripts for conditioned diffusion are (details)
292. fixed random conditionals plotting problem (details)
293. storage (using dill) and post processing of conditioned diffusion (details)
294. test numbers 1-4 in extra densities (details)
295. working on plotting of conditioned diffusion (details)
296. fixed bug in plotAlignedConditionals (details)
297. plotting (details)
298. forcing full span when rbf is chosen in default constructors (details)
299. condiff: fixed input span to (details)
300. testing higher order for cond diff (details)
301. fixed problem in aligned map plotting (details)
302. started with parallelization of diagnostics (details)
303. parallelization of the diagnostics (details)
304. cond diff: adaptation (details)
305. cond diff: adaptation works (details)
306. parallelization works for aligned conditionals (details)
307. working on cond diff example and figures (details)
308. plot with log log (details)
309. plotting diagnostic parallelized with mpi_map v1.0.3 (details)
310. updated conditioned diffusion postprocessing files (details)
311. added variance based diagnostic (details)
312. allow for restart in cond diff example (details)
313. working on restarting of cond diff (details)
314. plotting diagnostic now stack all the evaluation points together in (details)
315. added nprocs in adapted composition cond diff (details)
316. fixed bug in slice map plotting (details)
317. cond diff with restart works (details)
318. fixed problem in inverse which would cause loss of precision. cond diff (details)
319. started with the parallelization of variance_approx_kl. Changes are (details)
320. added Weibull density to the available test distributions (details)
321. moved all pc_density analytical stuff to ExtraDensities (details)
322. started with issue #41. made a sketch c++ module (details)
323. handling arrays Numpy/C done (details)
324. started with weird sampler (details)
325. sampler done (details)
326. working on construction from samples (details)
327. working on Laplace for cond diff (details)
328. working on plots cond diff (details)
329. some plotting progresses (details)
330. example for xun ready. Todo: document it.. (details)
331. added readme to the CPP-module example (details)
332. removed unnecessary files (details)
333. prepared figures for YMM presentation (details)
334. working on the direct approximation of the Weibull distribution (details)
335. log_pdf in extra doesn't work with algorithm, but algorithm is running (details)
336. working on map composition direct transport (details)
337. Weibull works. Added asymptotic behavior on the Logistic. (details)
338. starting with stochastic volatility (details)
339. working on step by step construction (details)
340. reordering in progress (details)
341. renamed files (details)
342. moving in the dark for Logistic and Banana examples... (details)
343. added installation tips in the documentation (details)
344. reorganizing example file organization (details)
345. fixed bug due to new version of SciPy rootfinding routine. tolerances (details)
346. rewriting the density (details)
347. sv density and data generation ready (details)
348. sv: Laplace done (details)
349. sv: composition of maps done, with postprocess (details)
350. sv: direct map done (details)
351. direct map in low dimension (details)
352. sv: inverse map construction (details)
353. algorithm working, with unnormalized data (details)
354. normalizing data, in progress (details)
355. sv working on the inverse map (details)
356. algorithm with renormalized data (details)
357. working on sv inverse (details)
358. added grad check on minimiziation. working on sv inverse... (details)
359. fixed bug on grad_a_inverse pushforward... (details)
360. sv inverse map preconditioned throught laplace pullback (details)
361. preparing dataset for Shwab (details)
362. algorithm tau change (details)
363. updated jenkins links (details)
364. reversed to v1.0.0 for initial releases (details)
365. data loading script for Robert done (details)
366. data loading for Robert works (details)
367. Added example with only the material for Shwab (details)
368. added test pullback for shwab material (details)
369. mc study of map parameters (details)
370. memory leak issue (details)
371. renamed variables (details)
372. sv: inverse map preconditioned with diagonal Laplace (details)
373. debugging memory leak (details)
374. added if conditions around logging outputs (details)
375. partially solved memory leak. There is still an issue with precomputed (details)
376. improved logging (details)
377. New stoc vol with hyperparameters doc (details)
378. fixing memory leak (details)
379. Done with the derivation of the  Stoc Vol model  with Hyper-params (details)
380. cleaned msf_kl_test file (details)
381. mc_sparsity.py (details)
382. post processing mc study (details)
383. diagnostics are now parallelized (details)
384. #45 added default constructors to examples. TODO: fix Gumbel (details)
385. Fixes #45 (details)
386. finished with default constructors examples (details)
387. post proc for mc study has S and Omega matrix and element-wise norms (details)
388. Implementing gradients Stoc Vol with Hyper-parameters (details)
389. caching passes unit tests. TODO: test on example and check speedup (details)
390. added time tracking for examples (details)
391. working on examples (details)
392. added timing in all the examples (details)
393. taking top-down approach. started with kl_divergence functions in (details)
394. variable elimination added but has bug, need to find cliques in matrix (details)
395. applied changes to all functions in Routines.py. TODO: think about the (details)
396. grid graph implemented (details)
397. designed a way to make chacing and batching work while parallelizing the (details)
398. working on parallel structures (details)
399. parallelization of kl_divergence done... maybe. (details)
400. working on parallel batching... (details)
401. working on parallel-batching... (details)
402. MPI implementation to be debugged (old and new unit tests) (details)
403. old unit tests work!! (details)
404. parallel evaluation of kl divergence work almost on all test cases.. (details)
405. parallelization now allows for the use of a pool of processors which are (details)
406. added unit tests for minimization. to be tested (details)
407. kl tests (details)
408. working on unit tests (details)
409. fixed test case for arctan parallel (details)
410. minimization tests passed (details)
411. Done with full joint  Stoc Vol with Hypers (details)
412. bug fixed. running all tests! (details)
413. fixed bugs! MPI works! TODO: update the examples (details)
414. Done with Markov Component of Stoc Vol with Hypers (details)
415. parallelization works on the examples. TODO: profiling (details)
416. fixed bug on unit tests (details)
417. speed up unit tests kl divergence (details)
418. parallelized precomputation and fixed bug in test_kl_divergence (details)
419. another bug in test_kl (details)
420. another bug in test_kl (details)
421. running tests on stochastic volatility with hyperparameters (details)
422. working on parallelization of generation of new samples (details)
423. parallelized generation of samples (details)
424. post-proc finds error, variance and bias (details)
425. fixed mpi_eval call in regression (details)
426. fixed bug regression (details)
427. removed parallelization in regression for now... opening #52 (details)
428. working on composition of maps (details)
429. working on stoch vol (details)
430. examples work without mpirun (details)
431. Fixes #53. (details)
432. optional matplotlib in examples (details)
433. updated testing script (details)
434. made matplotlib optional throughout the module (details)
435. added script for running on voyager.mit.edu (details)
436. working on stochvol (details)
437. working on cluster (details)
438. fixed bug in kl divergence unit tests (details)
439. working on cluster (details)
440. Added trim density on Stoc Vol Hyper (details)
441. map generation for density with hyper parameters (details)
442. working on postprocessing (details)
443. Fixed deepcopy issues with Stoc Vol (details)
444. working on cluster (details)
445. postprocessing step (details)
446. fix typo in Routines.py (details)
447. fixed map generation with hyper (details)
448. all tests pass (details)
449. changes made on hess_x_log_pullback. TODO: replicate on other hess_x (details)
450. Issue #31: removed construction of m x d x d x d x d tensor from (details)
451. working on #40: implementing the map-reduce scheme (details)
452. the map-reduce scheme works. Figure out why the number of processes (details)
453. Fixes #53: implements map-reduce scheme (details)
454. histograms of map and omega entries (details)
455. added the stochastic Laplace postprocessing for the hyperparamters case (details)
456. laplace approximation posprocess for hyper parameters (details)
457. Implemented Markov component stoc vol hyper (details)
458. added defaults for components with different basis and span (details)
459. ready to test (details)
460. fix bug on defaults (details)
461. almost testing (details)
462. fixes.. (details)
463. something is running (details)
464. Scripts composition stoc vol with hyper working (details)
465. fixed defaults (details)
466. working on unit tests for clusters (details)
467. Ready for full problem with 1hyper (details)
468. Ready for full problem with 1hyper (details)
469. unit tests on cluster work (details)
470. Fixes for full problem with 1hyper (details)
471. Stoc Vol Hyper--configuration for 2 hyper (details)
472. Stoc Vol Hyper--configuration for 2 hyper (details)
473. working on first variation examples (details)
474. working on example (details)
475. working on first variation (details)
476. fixed bug on defaults (details)
477. other bug.. (details)
478. added job number in submission script for clusters (details)
479. added voyager submission script (details)
480. Setup for 3hypers Stoc Vol (details)
481. Setup for 3hypers Stoc Vol (details)
482. very unsure on where to put the first variation implementation (details)
483. regression example works on python3 (details)
484. working on parallelization of regression (details)
485. regression is now parallel. TODO: implement map-reduce for regression (details)
486. warm start with skipping steps done. It should be tested first! (details)
487. Changes to plot and postprocessing (details)
488. histograms have no ticks or labels (details)
489. added data for 2hyper (details)
490. added results for 1hyper (details)
491. working on hypersonic. added lag on composition construction. (details)
492. Getting rid of the recursion for composition of maps (details)
493. Input NMC to post processing script (details)
494. first variation implemented. TODO: test it (details)
495. added mpi_pool argument to diagnostic functions. Changed design of (details)
496. fixed variance diagnostic routine (details)
497. fixed routine variance diagnostic (details)
498. data 3hyper (details)
499. working on refinement (details)
500. working on test case 2d (details)
501. fixed file TransportMapDensities. The PullBackDensity was defined (details)
502. pdf as exp(log_pdf) (details)
503. Fixes to post-processing trim script (details)
504. working on plots (details)
505. working on plots of the first variation (details)
506. Decoupled data analysis from plots (details)
507. working on plots of first variation 2d (details)
508. added diagonal transport map (details)
509. adaptivity works on banana (details)
510. adaptive refinement works on banana with hyper-cross enrichment (details)
511. working on the banana (details)
512. done with the banana example (details)
513. started with stochastic volatility (details)
514. added results 2 hyper (details)
515. working on adaptivity for stochastic volatility (details)
516. it somehow works on stoc vol 5 steps (details)
517. removed data from branch (details)
518. new enrichment and stopping strategy in first variation adaptivity. (details)
519. preparing sensitivity tests (details)
520. refinement routine done. to be tested (details)
521. working on full algorithm for adaptivity (details)
522. working on remove coefficients (details)
523. first variation approach designed (details)
524. added input arguments to scripts (details)
525. 2hyper map 100 (details)
526. refinement strategy includes check on sensitivity of variance diagnostic (details)
527. data for stoc vol 2 hypers n100 (details)
528. added analysis 2hyper 100steps (details)
529. working on figures (details)
530. working on plots (details)
531. map from samples notebook started (details)
532. post processing (details)
533. map from samples notebook, code fine but maybe should have more text (details)
534. moved samples notebook (details)
535. new storage for first variation script (details)
536. fixed storage adaptivity (details)
537. fixing adaptivity for quadratures (details)
538. working on examples for presentation (details)
539. added output on refinement (details)
540. improved total order multi index routine. (details)
541. added output to adaptivity (details)
542. getting data.. (details)
543. running conditionals for alessio (details)
544. improved postprocess (details)
545. fixed adaptivity routine (details)
546. right now the mpi design is a big mess... find an elegant way to get all (details)
547. restructuring all mpi calls according to the new design (details)
548. working on parallelization of objective functions (details)
549. objective done for integrated exponential... (details)
550. modifying regression routines. Todo also: fix the constraints in the (details)
551. done with code rewriting. TODO: rewrite all tests and examples. (details)
552. debuging: testing serial execution kl_divergence (details)
553. testing minimization serial (details)
554. minimization IE works. TODO: LS minimization and all parallel (details)
555. all serial tests work (details)
556. working on parallel tests (details)
557. testing parallel on kl_minimization and L2_minimization (details)
558. testing parallel on kl_minimization and L2_minimization (details)
559. passing all tests (details)
560. started with the documentation of MPI (details)
561. going on with docs (details)
562. fixed pdf/log_pdf for transprot map densities and going on with mpi (details)
563. working on example (details)
564. working on documentation (details)
565. working on documentation (details)
566. working on mpi examples (details)
567. working on mpi examples.... (details)
568. going on with mpi documentation. TODO: check examples... (details)
569. updated examples (details)
570. examples have been updated to use the new mpi interface (details)
571. updated slurm script for examples (details)
572. residual modifications to adaptivity routines (details)
573. fixed bug in mpi_eval (details)
574. working on examples (details)
575. updated regression examples to use MPI (details)
576. added action of hessian on routines and TransportMapBase. TODO: modify (details)
577. action of the Hessian implemented for the kl-divergence and the l2 (details)
578. finished last merge (details)
579. working on 3hyper (details)
580. fixed regression (details)
581. fixed chacing of hessian. Now it is really not recomputed (details)
582. fixed output hess (details)
583. fixed typo in routines (details)
584. batching implemented to be exthensively tested (details)
585. working on unittests for l2_misfit (details)
586. first test passed (details)
587. adding tests (details)
588. passing some of the tests... (details)
589. misfit tests all pass (details)
590. regression batching seems to work on unit test cases (details)
591. almost ready to run 3hyper on cluster (details)
592. almost ready to run 3hyper on cluster (details)
593. fixed runner (details)
594. removed data. use Dropbox folder for this (details)
595. logging capabilities improved for both kl-divergence and regression (details)
596. fixed scripts (details)
597. fixes #63 (details)
598. fixed serialization of the logger (un-pickable and thus removed from the (details)
599. added curvature output on Hessian output (to check positive (details)
600. mpi tutorial is done (details)
601. working on cpp examples (details)
602. updated stocvol analysis with new MPI (details)
603. updated construction scripts (details)
604. updated analysis (details)
605. udated plotting for stoc vol (details)
606. updated mpi-usage (details)
607. re-activated var_diag_list (details)
608. added debug code for Hessian conditioning (details)
609. added no-marginals option in plotting (details)
610. use gaussian graphs in algorithm (details)
611. working with generated data (details)
612. working on newly generated data (details)
613. fixed analysis script (details)
614. removed data folder durbin (details)
615. updating adaptivity to new MPI (details)
616. fixed merge with master. MPI functionalities updated (details)
617. added possibility of pulling back through Laplace prior to adapt the map (details)
618. improved postprocessing (details)
619. added possibiltiy do inverse adaptivity (details)
620. working on log-gauss Cox (details)
621. added test for processes (details)
622. working on log-cox densities (details)
623. working on logcox (details)
624. working on log-cox (details)
625. working on setup of log gaussian cox (details)
626. data generation done (details)
627. working on log gaussian cox (details)
628. plotting change in laplace postprocess (details)
629. added pieces of grad_a_omega (details)
630. testing new derivatives (details)
631. cleaning before merge (details)
632. fixes on the full transport maps (details)
633. reorganizing examples (details)
634. added Laplace scripts (details)
635. restructuring examples (details)
636. restructuring examples (details)
637. restructuring stochastic volatility example (details)
638. restructuring stochastic volatility (details)
639. restructuring LogGaussCox (details)
640. restructuring (details)
641. working on LogGaussianCox postprocessing for generic maps (details)
642. working on LogGaussianCox (details)
643. started working on script for generic transport map construction (details)
644. updated contributors list and author list in files (details)
645. updated readme (details)
646. updated readme (details)
647. working on direct map script (details)
648. started with xml specification of maps (details)
649. delta method almost done, fibers incorrect in TransportMapBase (details)
650. working on xml descriptors (details)
651. working on xml descriptor parsers (details)
652. updated authors and emails (details)
653. added xml loader for tests (details)
654. reduced dimension of linear map Hessian return (details)
655. updated authors and emails... (details)
656. working on constructor of linear span approximations (details)
657. working on the XML schema... (details)
658. working on the schema and validating it... (details)
659. working on the definition of a syntax for the components (details)
660. working on the definition of a syntax for the components (details)
661. working on basis (details)
662. added example structures (details)
663. working on the parser in TriangularTransportMaps.py (details)
664. working on the parser for IntegratedExpTriMap (details)
665. updated author and contact in init file (details)
666. parser.... (details)
667. sprinting on LogGaussianCoxProcess. The script tmap-direct will need to (details)
668. test was run successfully for nobs=30. the tmap-direct script is in (details)
669. working on independent samplers (details)
670. working on rejection sampler (details)
671. working on samplers (details)
672. working on effective sample size criteria... (details)
673. ess implemented (details)
674. working on postprocess scripts (details)
675. bigger head map for log gaussian cox (details)
676. working on the sampling of tmap (details)
677. almost done with figures for Log Gauss Cox (details)
678. working on Metropolis samples. Added h5py dependency (details)
679. tests gradahessxpartialxd (details)
680. one bug less to be fixed... (details)
681. added test_functions (details)
682. figures and scripts for log gauss cox are done (details)
683. added batching for tmap-postprocess but needs to be improved (details)
684. streamlining scripts for sequential inference postprocessing (details)
685. heavy modification of the postprocess scripts for stoch vol. Sequential (details)
686. scripts for paper working... (details)
687. working on postprocessing plotting (details)
688. merging (details)
689. prepared plotting for paper (details)
690. almost all figures are done (details)
691. Christmas plots (details)
692. working on figures (details)
693. working on parsing of IntExpNonLinearHeadMap-5d.xml (details)
694. working on parsing of IntExpNonLinearHeadMap-5d.xml (details)
695. working on functional approximations. Allow for the use of (details)
696. added the approx layer in order to mimic the class hierarchy (details)
697. think a better design for tensorized/non-tensorized basis... (details)
698. working on parsing of functionals (details)
699. working on tensorization of basis.... (details)
700. moving on to the parsing of basis (details)
701. constructor works for IntExpNonLinearHeadMap-5d.xml and (details)
702. removed HardVars which is cretated at sdist time (details)
703. added creation of hardcoded variables (xml schemes) at install and (details)
704. working on serializing xml unit tests. (details)
705. figure out how to define classes on the fly (details)
706. full order works (details)
707. monotonic lin span approximation get instantiated, but we need to add a (details)
708. tolerance computed with delta method (details)
709. working on RadialBasisFunctions support... Maybe we need to interface (details)
710. loading from xml works, but multi-index loading and xml storing (details)
711. construction of multi-idx map from xml works (details)
712. working on tests for scripts (details)
713. done with the tests for the scripts (details)
714. started working on integrated squared approximation (details)
715. working on test_transportmaps inverse.. (details)
716. working on kl divergence tests (details)
717. working on tests and examples (details)
718. test_xml works (details)
719. removed Full and Total order approximations. Now they are all (details)
720. starting the implementation of the integrated squared linear span (details)
721. working on the intsq approximation (details)
722. going on... (details)
723. progressing... (details)
724. we are over the hill.. (details)
725. Class IntegratedSquaredParametricFunctionApproximation done. TODO: (details)
726. test_transportmaps pass (details)
727. working on minimization tests... something wrong with batching.. (details)
728. working on int sq (details)
729. interfacing with PosDefConstSquaredExtHermitePhysicistsFunction (details)
730. something is wrong with the pos def squared implementation... (details)
731. working on test_transports for new Inetgrated Squared approximations (details)
732. squared const ext hermite prob func works but slow. To be profiled (details)
733. integrated squared is almost ready. Implementation sufficient for merge (details)
734. ordering and post-processing (details)
735. added functions needed for variance of omega, for algebraic basis (details)
736. added n_edges to graphs and normalized delta plots (details)
737. fixed postprocess script (details)
738. fixed input/raw_input (details)
739. working on additional functions for list composite map (details)
740. working on hess_x (details)
741. implemented ListCompositeTransportMap. It's missing some (details)
742. imporved documentation tmap-direct (details)
743. cleaning: mapsFromSamples dir (details)
744. working on scripts interface (details)
745. working on help for scripts (details)
746. working on scripts (details)
747. working on scripts (details)
748. algorithm with graphs is now test file (details)
749. working on postprocessing scripts (details)
750. fixed disclaimer LGPL (details)
751. tests work for the scripts in place. start docs. (details)
752. restructured documentation. Prepared for scripts documentation (details)
753. working on documentation of cli (details)
754. working on bod (details)
755. fixed references and working on bod (details)
756. working on unbiased samplers (details)
757. working on unbiased sampling (details)
758. data generation for bod (details)
759. done with bod (details)
760. done with bod (details)
761. working on xml docs (details)
762. xml docs done (details)
763. xml done (details)
764. xml done (details)
765. gumbel ready for presentation too (details)
766. fixed gumbel also for documentation (details)
767. added grad_x_inverse and log_deg_grad_x_inverse methods (details)
768. working on bod presentation (details)
769. going on with bod presentation (details)
770. almost done with bod (details)
771. bod for presentation ready (details)
772. done with tm examples (details)
773. done with xml (details)
774. started with cli (details)
775. started working on the stochastic volatility density... (details)
776. started with writing of classes for decomposable densities (details)
777. started with writing of classes for decomposable densities (details)
778. going on with densities (details)
779. working on classes for sequential inference (details)
780. working on rewriting stocvol densities (details)
781. wrapping up stocvol density (details)
782. testing new implementation! (details)
783. equivalent density! TODO: MarkovComponent (details)
784. working on markov component. (details)
785. working on markov comp (details)
786. one residual error in the hessian... (details)
787. The density is set up and ready to be used (details)
788. working on documentation and refactored examples of densities (details)
789. documenting stoc volatility (details)
790. going on with sequential inference example (details)
791. working on docs for stocvol example (details)
792. reorg, now with dirs (details)
793. fix directory for monte carlo run (details)
794. adding data dir (details)
795. removed tabulate (details)
796. fixed import for python2 (details)
797. added missing densities (details)
798. removed some example densities for now (details)
799. acme data clean (details)
800. working on stoc vol example (details)
801. working on first step stoc vol (details)
802. working on first step stoc vol (details)
803. almost done with stoch vol (details)
804. doing stoc vol post processing (details)
805. sequential inference needs a longer example (details)
806. started with SeqHMM integrator (details)
807. finished sequential inference... (details)
808. fixed imports of integrator. TODO: documentation of the integrator class (details)
809. fixed typos in examples (details)
810. added svg data assimilation (details)
811. added inkscape preamble (details)
812. updated figures and notation in sequential inference (details)
813. fixed pictures (details)
814. fixed bod (details)
815. working on filtering (details)
816. done with getting filtering out (details)
817. ok with filtering of stoc vol (details)
818. added the script for sequential inference (details)
819. first implementation of sampler works on postprocessing (details)
820. added stochastic volatility folder (details)
821. adding ess estimation in unbiased sampling script (details)
822. postprocess sampling fixed (details)
823. working on command line commands (details)
824. working on command line documentation! (details)
825. working on command line documentation! (details)
826. working on cli (details)
827. going on with cli (details)
828. working on cli postprocess (details)
829. working on cli postprocess (details)
830. cli done (details)
831. dummy file for volatility data (details)
832. added missing file (details)
833. fixing stile of documentation (details)
834. refactored Density->Distribution (details)
835. removed unused functions in Diagnostics.Plotting (details)
836. checked default constructors. fixes #34 (details)
837. added deprecation flag for old sub-module Denisities (details)
838. fixed logging of solving stats (details)
839. removed default dependency on optional packages (details)
840. disabled parallel tests if MPI is not supported (details)
841. downgraded documentation to TM 1.0 (details)
842. removed circular import in all the submodules (details)
843. local merge (details)
844. installation goes through on MAC. Going on with documentation (details)
845. working on intro (details)
846. checking for broken links (details)
847. fixing readme (details)
848. fixed wrong merge.. (details)
849. working on alinged-marginals. Check on quadratures output as well. (details)
850. added marginal plotting (details)
851. sequential-tm with restart (details)
852. tmap-sequential-tm can now re-start. Added verbose options and (details)
853. working on postprocess for sequential algorithm (details)
854. added postprocess for sequential inference (details)
855. done with scripts (details)
856. working on documentation of inverse from samples (details)
857. working on inverse sparse transport (details)
858. added inverse stochastic volatility example (details)
859. added figures for cli.ipynb (details)
860. working on class diagram (details)
861. working on the api (details)
862. removed autosummary (details)
863. included inheritance graph. Fixes #27 (details)
864. fixed dictionary get for python2. Fixes #75 (details)
865. updated version 1.0.0b1 and copyright (details)
866. updated info (details)
867. working on upload script (details)
868. working on release testpypi (details)
869. modified warning for non-supported features (details)
870. fixed linking to SpectralToolbox. Now it is done at first import (details)
871. fixed issue in frozen distributions. v1.0.0b4 (details)
872. fixed xml linking (details)
873. fixed test_xml and test_scripts (details)
874. fixed some settings for unit tests failing on kl-divergence due to fd (details)
875. refactoring Examples for release (details)
876. cleaning up before release (details)
877. working on mirroring (details)
878. after moving (details)
879. working on public mirroring (details)
880. working on public mirroring (details)
881. added deprecated frozen denisties (details)
882. working on mirror (details)
883. workin on mirroring (details)
884. fixed (maybe) base_density/base_distribution inconsistency (details)
885. fixed (again maybe) base_density/base_distribution inconsistency (details)
886. mirroring script ready (details)
887. fixed readme (details)
888. bitbucket-pipelines.yml created online with Bitbucket (details)
889. bitbucket-pipelines.yml edited online with Bitbucket (details)
890. bitbucket-pipelines.yml edited online with Bitbucket (details)
891. bitbucket-pipelines.yml edited online with Bitbucket (details)
892. bitbucket-pipelines.yml edited online with Bitbucket (details)
893. bitbucket-pipelines.yml edited online with Bitbucket (details)
894. bitbucket-pipelines.yml edited online with Bitbucket (details)
895. bitbucket-pipelines.yml edited online with Bitbucket (details)
896. bitbucket-pipelines.yml edited online with Bitbucket (details)
897. bitbucket-pipelines.yml deleted online with Bitbucket (details)
898. working on jenkins script (details)
899. testing push with jenkins (details)
900. updated jenkins script (details)
901. fixing pip for long path.. not really needed for tests on bitbucket (details)
902. jenkins... (details)
903. jenkins... (details)
904. jenkins... (details)
905. jenkins... (details)
906. jenkins... (details)
907. jenkins... (details)
908. jenkins... (details)
909. jenkins... (details)
910. jenkins... (details)
911. jenkins... (details)
912. jenkins... (details)
913. Jenkins config: testing test_scripts (details)
914. fixed logging of solving stats (details)
915. Jenkins tests (details)
916. Jenkins... (details)
917. Jenkins... (details)
918. Jenkins... (details)
919. Jenkins... (details)
920. Jenkins... (details)
921. Jenkins... (details)
922. Jenkins... (details)
923. Jenkins... (details)
924. Jenkins... (details)
925. Jenkins: exit(1) if packages failed (details)
926. removed cached dir (details)
927. Jenkins... working on setup (details)
928. jenkins.. (details)
929. jenkins.. (details)
930. jenkins... (details)
931. jenkins... (details)
932. jenkins testing all (details)
933. updated email (details)
934. removed e-mail contact (details)
935. updated readme (details)
936. updated readme (details)
937. updated readme (details)
938. reduce verbosity in tests (details)
939. updated scripts and logging (details)
940. fixed logging (details)
941. removed MPI support for macys-Sierra (details)
942. fixed log levels.. (details)
943. fixed errors in grad_a_hess_x and grad_a_hess_x_log_det_grad_x (details)
944. removed tests for grad_a_hess_x_log_det_grad_x. Filed issue #76 (details)
945. updated parallelization and fixed failing test in test_kl_divergence (details)
946. fixing test_kl_divergence (maybe) (details)
947. turning MPI=True on Macys-Sierra (details)
948. fixed linear map in IS kl_divergence (details)
949. added jenkins tests for testpypi (details)
950. modified linear2d test in order to make it more amenable for PushForward (details)
951. simplified setup.py (standardized) (details)
952. the user is now required to pre-install numpy (details)
953. fixed jenkins script (details)
954. removed hardvars (details)
955. removed hardvars (details)
956. removed pushforward kl_div tests (details)
957. split serial and parallel tests (details)
958. testing serial (details)
959. added mpi option (details)
960. fixed check on mpi in jenkins (details)
961. added lag on mpi tests in order to accommodate for closing and opening (details)
962. set unique random seed=1 (details)
963. adding badges to the documentation (details)
964. disabled MPI on sierra (details)
965. relaxed check on l2 minimization tolerance (details)
966. updated badges and upload code (details)
967. lower tolerance on transportmap_distributions (details)
968. fixed namespace and restored tolerance in transportmap_distributions (details)
969. updating index (details)
970. added verbose output for failed finite difference (details)
971. added verbose output for failed finite difference (details)
972. set integrated squared to linear for test_transportmap_distributions (details)
973. extending readme (details)
974. README.rst edited online with Bitbucket (details)
975. README.rst edited online with Bitbucket (details)

New stoc vol file

Done with implementation stochastic volatility with no hyper-parameters

Stochastic volatility

answers to Alessio comments

started with solver

stoc vol works. TODO: implement diagnostics

started with total order implementation

working on MixedOrder class.

working on mixed order

working on MixedOrder

Added diagnostic routines

merged into toolbox

working on stocVol example

stocVol

stocVol

added matplotlib dependency

working on banana example

documenting banana

working on banana

working on banana example

banana example needs documentation regarding diagnostics

added some diagnostics

working on laplace_approximation function

laplace

working on optimizer

Laplace approx done. To be tested.

working on FrozenGaussian with precision input

tests passed for new version of GaussianDensity. TODO: add unittests
with precision matrix

done precision tests

laplace works. to finish tests

laplace works. to finish tests

laplace works. to finish tests

Laplace ready

test optimizer

working on optimizer

fixed optimizer

optimizer works!

added some docs on banana

added some logging in the Diagnostic module. To be added all over.
Completed direct examples. Todo: check plotAlignedConditionals in 1d and
accuracyIntegratedExponential seem to have little effect...

newton_cglu_optimizer

added function niceplot

Added class TransportMap

class TransportMap integrated

Init maps

working on the CommonBase LinearSpan TM

Removed duplicate pullback functions

working on CommonBase LinearSpan Map

linear transport map

fixed naming of TransportMaps

working on CommonBase LinearSpan Map

working on CommonBase LinearSpan Map

Done CommonBasis LinearSpan Map. Moving to
CommonBasisLinearSpanApproximation

working on CommonBasisLinearSpanApproximation

working on CommonBasisLinearSpanApproximation

working on CommBase Map

moving function evaluation and gradients into LineaSpanAppoximation
class. These methods either take lists of uni-variate vandermode
matrices or the composed vandermonde matrix

Done with linear map class. Now moving to unit test

in process of migrating functions from FullLinearSpan to LinearSpan with
multi_idx

moved most of the stuff to LinearSpan

moved most of the stuff to LinearSpan

LinearSpanApproximations ready. Move to TriangularTransportMap

Minor changes

changed uml

Added plotAlignedSliceMap

Added niceContour, plot2density and testBananaPullback

added testBananaPullback

fixed l2 regularization

rotated banana improved

working on #36. Done with Transport maps?

Banana example linear span

some mods on the examples

#26 working on TM densities test cases

working on test cases

working on test cases

working on density test cases

working on test cases for densities

working on dens test cases

working on tests densities

transport map densities tests added. Still some problems on the linear
map tests (grad_a, hess_a unstable for high order)

added tests for kl_divergence

removed old tests structure

#26 fixed all unittests. TODO add test for LinearTransportMap (Alessio)

updating UML graph and TransportMap classes

Fixes #27: UML graph updated

fixed import name for CommonBasisLinearSpanTriangularTransportMap

relaxed target eps in MC tests for density unittests

Jenkins test develop script added

fixed test_develop chmod

#25 restructuring precomp strategy in order to enrich the precomp
dictionary. evaluate() in LinearApproximationBase.py is done

#25 restructuring precomp strategy in order to enrich the precomp
dictionary. evaluate, grad_x, hess_x in LinearApproximationBase.py are
done

#25 restructuring precomp strategy in order to enrich the precomp
dictionary. evaluate, grad_x, hess_x in LinearApproximationBase.py are
done

uni-variate preallocation works for linear system

working on TransportMapBase to allow both uni-variate and multi-variate
precomputation

working on TransportMapBase to allow both uni-variate and multi-variate
precomputation

#25 linear span transport maps with precomputation of uni-variate and
multi-variate Vandermonde done (with unittests). TODO: Start to work on
IntegratedExponential and CommonBasisLinearSpan.

working on IntegratedExp approximation

working on IntegratedExp approximation

working on IntegratedExp approximation

working on precomputation in integrated exponential. Some tests fail...

#25 preomputation on integrated exponential works! Make comprehensive
tests for TM densities. Moving to CommonBasis classes

fixed FrozenFunction precomp functions

KLdivergence example with options

working on common basis

working on common basis

fixing common basis

CommonBasisLinearSpan ready. TODO: unittests

making unittests for CommonBasisLinearSpan

fixed stoc Vol with constant term

CommonBasis LinearSpan works. Moving to IntegratedExponential

CommonBasisIntExp started. precomp_evaluate done

IntExpFunctionApproximation precomputation structure refactorization
started

refactored IntExpFuncApproximation

working on CommonBasis IntegExp

CommonBasis IntegratedExponential works

KLdivergence example now uses CommonBasis implementation

Fixes #25.

updated banana example with common basis

TotalOrder approximation added. Fix the integration into IntExp
approximation where the constant part must have order 0 wrt the last
dimension

Total order working on test_transportmaps. TODO: Add
test_transport_map_densities tests and try this out on experiments

Total Order unittests done

fixed CommonBasis precomputation, adding to_compute_flag

Fixes #1. Total order truncation implemented. Updated KLdivergence
example and fixed a bug on Issue #25.

Added BOD model and ConditionedDiffusion folders

fixed conflict on testBananaPullback

started with new branch

fixed bug on GaussianDensity rvs

fixed bug on GaussianDensity rvs

working on stochastic volatility example

Added joint BOD model

reshaping StochasticVolatility example

BOD model works.

Stochastic volatility issuing command changed

#31 started optional vectorization of expectations in
PushForwardTransportMapDensity.minimize_kl_divergence

Notes composition map Stoc Vol

Added banana folder

starting with stoc vol composition

split map generation from StochasticVolatility files

Added gradients composition

Added gradients composition

Added Markov Component Stoc Vol

stoc vol composition almost there....

stoc vol composition runs. TODO: compose all the maps

working on lifting and overall pullback

stochastic volatility composition works!!!

refactoring the vectorization in several routines... to be finished.
TODO: allow the evaluation to be done in batches.

#31 refactoring to allow computations in batches

refactored everything to execute in batches defined by a list (iterable)

new implementation works on old unit tests

current implementation works on unittests and KLdivergence example test
cases with batched vectorization

setting up BOD model for higher dimension...

Opens #20. Added logging capabilities in the minimize_kl_divergence
functions

working on BOD higher order

working on bod

working on KL divergence arctan function

cleaned KL divergence file

re-organized predefined densities

added corresponding changes also in the LinearTransportMap class

working on the tilted banana

updating LinearTransportMap

updating LinearTransportMap

working on banana

added default classes for Isotropic transport maps

added default classes for Isotropic transport maps

using default functions all over

working on rotated banana

#35 working on cached evaluations low-level

#35 low-level caching for function evaluation implemented. TODO: check
that it does what we want...

removed some all-equal statements

changed handling of indices

caching low level partial_xd done

changed array_equal withing function evaluation with a same_coeffs_flag
which is broadcasted top down

fixed FrozenTriangularTransportMaps

Gradients conditional diffusion

working on conditioned diffusion script. fixed inputs to StocVol

conditioned diffusion running script ready

using default TransportMap generation all over the place

Implemented gradients Markov Component Cond Diff

working on fixing stochastic volatility components. TODO: Fix the
LinearTransportMap to make it accept the same_coeffs_flag argument

fixed full transport map with extra same_coeffs_flag

Debugging Hessian CondDiff

Fixed gradient Markov Component Conditioned Diffusion

Added composition maps for conditione diffusion

working on conditioned diffusion

FullTransportMap does not need to redefine pullback and pushforward
functions

cond diffusion works. better parametrization is needed (RBF?)

can recover precision matrix in 3d

updating UML diagram

map from samples now has a couple more distributions to sample from

mapFromSamples also plots histograms of pullback against original
samples

removed "TranportMaps." tag from index

compare map to analytical

histogram plots a bit nicer

working on using RBF in banana example

preparing for high-level caching. Restructured precomp structure

high-level caching is done. TODO: check it is doing what is required to